About the mafia kajita tag
mafia kajita is a character tag that NovelAI Diffusion can use. On Danbooru it has 323 posts, and its best-rated still image scores 49. The samples above put the tag at the front of a fixed base prompt with seed 1234, so the differences between tags come from the tag alone.
How each model draws mafia kajita
Follows composition and expression instructions closely, so the effect shows in a tidy form.
Reacts to the tag more strongly, so its effect is easier to see.
WAI illustrious SDXL v17, a local model. Shows how the same tag reads outside NovelAI.
Writing mafia kajita in a prompt
Put the subject first, then this tag, then quality tags.
mafia kajita, solo, best quality, masterpiecewlop, mafia kajita, soloThe negative prompt and the full settings are on the terms page.
How these samples were made
Every image uses 832×1216, seed 1234, 23 steps and the k_euler_ancestral sampler. The base prompt and negative prompt stay the same for every tag, and only the tag under test changes. Images flagged by the NSFW check are regenerated with a new seed or hidden.
From the Danbooru wiki
Show the wiki text ▾Hide ▴
Mafia Kajita (real name: Kajita Ryuuki) is a freelance writer who has been involved in many game, anime, and manga projects. He is also noted for his distinct appearance - bald head, sunglasses, mustache, and leather jacket. Kajita is friends with many seiyuu, notably Sugita Tomokazu on whose radio show he regularly appears as a guest, and Nakamura Yuuichi with whom he has a radio-style YouTube channel.
SP Tanaka is an alternate personality of his.
He is co-creator of the Goho Mafia! Kajita-kun manga by providing its material.
FAQ
Does NovelAI recognize mafia kajita?
Compare the samples on this page. Every tag on this site shares the same seed and base prompt, so any change you see comes from mafia kajita.
How do I write mafia kajita in a prompt?
Write "mafia kajita" near the front of the prompt and separate it from other tags with commas.
Should I use V5 or V4.5?
V4.5 shows the tag's effect more strongly. V5 gives steadier images with fewer artifacts.